| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003919263178522438, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.919263178522438e-05, | |
| "grad_norm": 1.6733793020248413, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.919263178522438e-05, | |
| "eval_loss": 3.0779740810394287, | |
| "eval_runtime": 481.9446, | |
| "eval_samples_per_second": 22.293, | |
| "eval_steps_per_second": 11.147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.838526357044875e-05, | |
| "grad_norm": 1.5507906675338745, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011757789535567314, | |
| "grad_norm": 1.7221944332122803, | |
| "learning_rate": 6e-05, | |
| "loss": 3.086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011757789535567314, | |
| "eval_loss": 3.055471420288086, | |
| "eval_runtime": 489.7308, | |
| "eval_samples_per_second": 21.939, | |
| "eval_steps_per_second": 10.969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001567705271408975, | |
| "grad_norm": 1.660340666770935, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8378, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001959631589261219, | |
| "grad_norm": 1.6775951385498047, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00023515579071134627, | |
| "grad_norm": 1.7437950372695923, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8443, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023515579071134627, | |
| "eval_loss": 2.8309810161590576, | |
| "eval_runtime": 320.8183, | |
| "eval_samples_per_second": 33.489, | |
| "eval_steps_per_second": 16.745, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027434842249657066, | |
| "grad_norm": 1.8472623825073242, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9914, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000313541054281795, | |
| "grad_norm": 1.1509668827056885, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5826, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003527336860670194, | |
| "grad_norm": 1.33197021484375, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4184, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003527336860670194, | |
| "eval_loss": 2.585024356842041, | |
| "eval_runtime": 443.6609, | |
| "eval_samples_per_second": 24.217, | |
| "eval_steps_per_second": 12.108, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003919263178522438, | |
| "grad_norm": 1.361803412437439, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5364, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |